Abstract: Numerous examples are disclosed of a masking circuit for inputs and outputs in a neural network array. In one example, a system comprises a neural network array comprising a plurality of non-volatile memory cells arranged into rows and columns; and row circuits for respective rows in the neural network array, the row circuits comprising a masking circuit to prevent an application of a sparse input to one or more rows in the array when a condition is satisfied.

Abstract: In one example disclosed herein, a system comprises an analog computation-in-memory engine to perform operations in a first layer in a neural network and a digital computation-in-memory engine to perform operations in a second layer different than the first layer in the neural network. The system optionally comprises a dynamic weight engine to perform operations in a third layer different than the first layer and the second layer in the neural network.

Abstract: Numerous examples are disclosed for an output block coupled to a non-volatile memory array in a neural network and associated methods. In one example, a circuit for converting a current in a neural network into an output voltage comprises a non-volatile memory cell comprises a word line terminal, a bit line terminal, and a source line terminal, wherein the bit line terminal receives the current; and a switch for selectively coupling the word line terminal to the bit line terminal; wherein when the switch is closed, the current flows into the non-volatile memory cell and the output voltage is provided on the bit line terminal.

Abstract: Numerous embodiments of decoders for use with a vector-by-matrix multiplication (VMM) array in an artificial neural network are disclosed. The decoders include bit line decoders, word line decoders, control gate decoders, source line decoders, and erase gate decoders. In certain embodiments, a high voltage version and a low voltage version of a decoder is used.

Abstract: In one example, a method comprises erasing at the same time a word of non-volatile memory cells in an array of non-volatile memory cells arranged into rows and columns, each non-volatile memory cell comprising a word line terminal, a bit line terminal, and an erase gate terminal, by turning on an erase gate enable transistor coupled to erase gate terminals of the word of non-volatile memory cells.

Abstract: Numerous embodiments for reading or verifying a value stored in a selected memory cell in a vector-by-matrix multiplication (VMM) array in an artificial neural network are disclosed. In one embodiment, an input comprises a set of input bits that result in a series of input signals applied to a terminal of the selected memory cell, further resulting in a series of output signals that are digitized, shifted based on the bit location of the corresponding input bit in the set of input bits, and added to yield an output indicating a value stored in the selected memory cell.

Abstract: A neural network device with synapses having memory cells each having a floating gate and a first gate over first and second portions of a channel region disposed between source and drain regions, and a second gate over the floating gate or the source region. First lines each electrically connect the first gates in one of the memory cell rows, second lines each electrically connect the second gates in one of the memory cell rows, third lines each electrically connect the source regions in one of the memory cell rows, and fourth lines each electrically connect the drain regions in one of the memory cell columns. The synapses receive a first plurality of inputs as electrical voltages on the fourth lines, and provide a first plurality of outputs as electrical currents on the third lines.

Abstract: In one example, a system comprises an array of non-volatile memory cells arranged into rows and columns, the array comprising a first bit line coupled to a first column of non-volatile memory cells and a second bit line coupled to a second column of non-volatile memory cells; and an output block coupled to the array, the output block comprising: a current-to-voltage converter to convert a first current on the first bit line into a first voltage and to convert a second current on the second bit line into a second voltage; and an analog-to-digital converter to convert one or more of the first voltage and the second voltage into a set of output bits.

Abstract: A neural network device with synapses having memory cells each having a floating gate and a first gate over first and second portions of a channel region disposed between source and drain regions, and a second gate over the floating gate or the source region. First lines each electrically connect the first gates in one of the memory cell columns, second lines each electrically connect the second gates in one of the memory cell rows, third lines each electrically connect the source regions in one of the memory cell rows, and fourth lines each electrically connect the drain regions in one of the memory cell columns. The synapses receive a first plurality of inputs as electrical voltages on the first or fourth lines, and provide a first plurality of outputs as electrical currents on the third lines.

Abstract: A neural network device with synapses having memory cells each having a floating gate and a first gate over first and second portions of a channel region between source and drain regions, and a second gate over the floating gate or the source region. First lines each electrically connect the first gates in one of the memory cell rows, second lines each electrically connect the second gates in one of the memory cell rows, third lines each electrically connect the source regions in one of the memory cell rows, fourth lines each electrically connect the drain regions in one of the memory cell columns, and a plurality of transistors each electrically connected in series with one of the fourth lines. The synapses receive a first plurality of inputs as electrical voltages on gates of the transistors, and provide a first plurality of outputs as electrical currents on the third lines.

Abstract: Numerous embodiments of a transceiver for providing high voltages for use during erase or program operations in a non-volatile memory system are disclosed. In one embodiment, a transceiver comprises a PMOS transistor and a native NMOS transistor. In another embodiment, a transceiver comprises a PMOS transistor, an NMOS transistor, and a native NMOS transistor.

Abstract: Numerous output circuits are disclosed for an analog neural memory system for a deep learning neural network. In one embodiment, an adaptable neuron circuit receives output current from a neuron and converts it into a voltage. In another embodiment, a current sample and hold circuit samples an input current and generates an output current. In another embodiment, a voltage sample and hold circuit samples an input voltage and generates an output voltage.

Abstract: In one example, a system comprises a current-to-voltage converter to generate differential voltages from differential currents comprising a first current and a second current, the current-to-voltage converter comprising: a first bitline to provide the first current; a second bitline to provide the second current; a first regulator to apply a first voltage to the first bitline; a second regulator to apply a second voltage to the second bitline; a regulating circuit comprising a first input terminal, a second input terminal, a first output terminal, and a second output terminal, the first output terminal and the second output terminal providing the differential voltages; and a common mode circuit.

Abstract: Numerous examples of summing circuits for a neural network are disclosed. In one example, a circuit for summing current received from a plurality of synapses in a neural network comprises a voltage source; a load coupled between the voltage source and an output node; a voltage clamp coupled to the output node for maintaining a voltage at the output node; and a plurality of synapses coupled between the output node and ground; wherein an output current flows through the output node, the output current equal to a sum of currents drawn by the plurality of synapses.

Abstract: Numerous embodiments are provided for compensating for drift error in non-volatile memory cells within a VMM array in an analog neuromorphic memory system. For example, in one embodiment, a circuit is provided for compensating for drift error during a read operation, the circuit comprising a data drift monitoring circuit coupled to the array for generating an output indicative of data drift; and a bitline compensation circuit for generating a compensation current in response to the output from the data drift monitoring circuit and injecting the compensation current into one or more bitlines of the array.

Abstract: In one example, a system comprises a neural network array of non-volatile memory cells arranged in rows and columns; and a logical cell comprising a first plurality of non-volatile memory cells in a first row of the array and a second plurality of non-volatile memory cells in a second row adjacent to the first row; wherein the first plurality of non-volatile memory cells and the second plurality of non-volatile memory cells are configured as one or more coarse cells and one or more fine cells.

Abstract: Numerous examples are disclosed of multiplexors coupled to rows in a neural network array. In one example, a system comprises a neural network array of non-volatile memory cells comprising i rows, where i is a multiple of 2; j row registers, where j<i; j digital-to-analog converters to convert j sets of digital data received from the j row registers into j analog signals; and j multiplexors to route the j analog signals to a subset of the i rows in response to a control signal.

Abstract: Numerous examples are disclosed of systems and methods to implement redundancy. In one example, a system comprises an array of non-volatile memory cells; a redundant array of non-volatile memory cells; and an input block coupled to respective rows in the array and respective rows in the redundant array and comprising row tag registers and redundant row tag registers.

Abstract: A memory cell array having rows and columns of memory cells with respective ones of the memory cells including spaced apart source and drain regions formed in a semiconductor substrate with a channel region extending there between, a floating gate over a first portion of the channel region, a select gate over a second portion of the channel region, and an erase gate over the source region. A strap region is disposed between first and second pluralities of the columns. For one memory cell row, a dummy floating gate is disposed in the strap region, an erase gate line electrically connects together the erase gates of the memory cells in the one row and in the first plurality of columns, wherein the erase gate line is aligned with the dummy floating gate with a row direction gap between the erase gate line and the dummy floating gate.

Abstract: Numerous embodiments of programming, verifying, and reading systems and methods for use with a vector-by-matrix multiplication (VMM) array in an artificial neural network are disclosed. Selected cells can be programmed and verified with extreme precision to hold one of N different values. During a read operation, the system determines which of the N different values is stored in a selected cell.